Description

• Title:
  FORECASTING VIA WAVELET SMOOTHING
• Creator:
  Bruzda, Joanna
• Description:
  In the paper we discuss existing techniques for univariate time series forecasting based on the wavelet transform and introduce also a new method of forecasting with wavelets. The new approach is based on a nonparametric estimation of a stochastic signal via a wavelet smoothing. The method can be thought of as a wavelet variant of the exponential smoothing, which is, however, much more universal, being at the same time relatively computationally efficient. Our empirical verification based on 17 time series from the M3-JIF-Competition database provides very promising results, confirming the practical relevance of the suggested approach.
• Object availability:
  free access
• Date:
  2013.02.07
• Type:
  info:eu-repo/semantics/article;
  info:eu-repo/semantics/publishedVersion
• Language:
  Polish
• Source:
  Acta Universitatis Nicolai Copernici. Zarządzanie; Tom 39 (2012); 77-95;
  Acta Universitatis Nicolai Copernici. Management; Vol. 39 (2012); 77-95;
  2450-7040;
  1689-8966
• Format:
  application/pdf
• Publisher:
  Uniwersytet Mikołaja Kopernika w Toruniu
• Relation: https://apcz.umk.pl/AUNC_ZARZ/article/view/AUNC_ZARZ.2012.006/234
• Subject:
  wavelet forecasting;
  nonparametric signal estimation;
  wavelet smoothing;
  prognozy falkowe;
  nieparametryczna estymacja sygnałów;
  przeskalowywanie falkowe
• Identifier: https://apcz.umk.pl/AUNC_ZARZ/article/view/AUNC_ZARZ.2012.006
• Data provider:
  Akademicka Platforma Czasopism
• Can I use it?:
  seek permission
• Type:
  text